English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Graphs can model complex relationships between objects, enabling a myriad ofWeb applications such as online page/article classification and socialrecommendation. While graph neural networks(GNNs) have emerged as a powerfultool for graph representation learning, in an end-to-end supervised setting,their performance heavily rely on a large amount of task-specific supervision.To reduce labeling requirement, the "pre-train, fine-tune" and "pre-train,prompt" paradigms have become increasingly common. In particular, prompting isa popular alternative to fine-tuning in natural language processing, which isdesigned to narrow the gap between pre-training and downstream objectives in atask-specific manner. However, existing study of prompting on graphs is stilllimited, lacking a universal treatment to appeal to different downstream tasks.In this paper, we propose GraphPrompt, a novel pre-training and promptingframework on graphs. GraphPrompt not only unifies pre-training and downstreamtasks into a common task template, but also employs a learnable prompt toassist a downstream task in locating the most relevant knowledge from thepre-train model in a task-specific manner. Finally, we conduct extensiveexperiments on five public datasets to evaluate and analyze GraphPrompt.

GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks